INDEX

Explanations

terms related to scientific studies and their results

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.48

↵↵

-0.47

]]]

-0.45

↵↵↵

-0.43

TagMode

-0.39

 Edition

-0.38

azza

-0.38

onesian

-0.37

apore

-0.36

</blockquote>

-0.35

POSITIVE LOGITS

脚注の使い方

1.05

 disambiguazione

0.89

 estekak

0.88

ніципалі

0.84

WriteBarrier

0.80

httphttps

0.80

smithy

0.78

anyahu

0.77

 utafitiHapana

0.77

 насељу

0.77

Activations Density 8.352%

terms related to scientific studies and their results

No Comments

No Known Activations